spark的运行指标监控

abstract class SparkListener extends SparkListenerInterface {
//stage完成的时调用
  override def onStageCompleted(stageCompleted: SparkListenerStageCompleted): Unit = { }

//stage提交时调用
  override def onStageSubmitted(stageSubmitted: SparkListenerStageSubmitted): Unit = { }

  override def onTaskStart(taskStart: SparkListenerTaskStart): Unit = { }

  override def onTaskGettingResult(taskGettingResult: SparkListenerTaskGettingResult): Unit = { }
//task结束时调用
  override def onTaskEnd(taskEnd: SparkListenerTaskEnd): Unit = { }

  override def onJobStart(jobStart: SparkListenerJobStart): Unit = { }

  override def onJobEnd(jobEnd: SparkListenerJobEnd): Unit = { }

  override def onEnvironmentUpdate(environmentUpdate: SparkListenerEnvironmentUpdate): Unit = { }

  override def onBlockManagerAdded(blockManagerAdded: SparkListenerBlockManagerAdded): Unit = { }

  override def onBlockManagerRemoved(
      blockManagerRemoved: SparkListenerBlockManagerRemoved): Unit = { }

  override def onUnpersistRDD(unpersistRDD: SparkListenerUnpersistRDD): Unit = { }

  override def onApplicationStart(applicationStart: SparkListenerApplicationStart): Unit = { }

  override def onApplicationEnd(applicationEnd: SparkListenerApplicationEnd): Unit = { }

  override def onExecutorMetricsUpdate(
      executorMetricsUpdate: SparkListenerExecutorMetricsUpdate): Unit = { }

  override def onExecutorAdded(executorAdded: SparkListenerExecutorAdded): Unit = { }

  override def onExecutorRemoved(executorRemoved: SparkListenerExecutorRemoved): Unit = { }

  override def onBlockUpdated(blockUpdated: SparkListenerBlockUpdated): Unit = { }

  override def onOtherEvent(event: SparkListenerEvent): Unit = { }
}

case class SparkListenerTaskEnd(
                                 //spark的stageId
                                 stageId: Int,
                                 //尝试的阶段Id(也就是下级Stage?)
                                 stageAttemptId: Int,
                                 taskType: String,
                                 reason: TaskEndReason,
                                 //task信息
                                 taskInfo: TaskInfo,
                                 // task指标
                                 @Nullable taskMetrics: TaskMetrics)
  extends SparkListenerEvent

/**
 * 需求1.想自定义spark的job运行情况存入redis，集成到自己的业务后台展示中
 */
class MySparkAppListener extends SparkListener with Logging {

  val redisConf = "jedisConfig.properties"

  val jedis: Jedis = JedisUtil.getInstance().getJedis

  //父类的第一个方法
  override def onTaskEnd(taskEnd: SparkListenerTaskEnd): Unit = {
    //在 onTaskEnd方法内可以获取的信息有
    /**
     * 1、taskMetrics
     * 2、shuffle
     * 3、task运行（input output）
     * 4、taskInfo
     **/

    val currentTimestamp = System.currentTimeMillis()
    // TaskMetrics（task的指标）可以拿到的指标
    /**
     * private val _executorDeserializeTime = new LongAccumulator
     * private val _executorDeserializeCpuTime = new LongAccumulator
     * private val _executorRunTime = new LongAccumulator
     * private val _executorCpuTime = new LongAccumulator
     * private val _resultSize = new LongAccumulator
     * private val _jvmGCTime = new LongAccumulator
     * private val _resultSerializationTime = new LongAccumulator
     * private val _memoryBytesSpilled = new LongAccumulator
     * private val _diskBytesSpilled = new LongAccumulator
     * private val _peakExecutionMemory = new LongAccumulator
     * private val _updatedBlockStatuses = new CollectionAccumulator[(BlockId, BlockStatus)]
     */
    val metrics = taskEnd.taskMetrics
    val taskMetricsMap = scala.collection.mutable.HashMap(
      "executorDeserializeTime" -> metrics.executorDeserializeTime, //executor的反序列化时间
      "executorDeserializeCpuTime" -> metrics.executorDeserializeCpuTime, //executor的反序列化的 cpu时间
      "executorRunTime" -> metrics.executorRunTime, //executoor的运行时间
      "resultSize" -> metrics.resultSize, //结果集大小
      "jvmGCTime" -> metrics.jvmGCTime, //
      "resultSerializationTime" -> metrics.resultSerializationTime,
      "memoryBytesSpilled" -> metrics.memoryBytesSpilled, //内存溢写的大小
      "diskBytesSpilled" -> metrics.diskBytesSpilled, //溢写到磁盘的大小
      "peakExecutionMemory" -> metrics.peakExecutionMemory //executor的最大内存
    )

    val jedisKey = "taskMetrics_" + {
      currentTimestamp
    }
    jedis.set(jedisKey, Json(DefaultFormats).write(jedisKey))
    jedis.pexpire(jedisKey, 3600)


    //======================shuffle指标================================
    val shuffleReadMetrics = metrics.shuffleReadMetrics
    val shuffleWriteMetrics = metrics.shuffleWriteMetrics

    //shuffleWriteMetrics shuffle读过程的指标有这些
    /**
     * private[executor] val _bytesWritten = new LongAccumulator
     * private[executor] val _recordsWritten = new LongAccumulator
     * private[executor] val _writeTime = new LongAccumulator
     */
    //shuffleReadMetrics shuffle写过程的指标有这些
    /**
     * private[executor] val _remoteBlocksFetched = new LongAccumulator
     * private[executor] val _localBlocksFetched = new LongAccumulator
     * private[executor] val _remoteBytesRead = new LongAccumulator
     * private[executor] val _localBytesRead = new LongAccumulator
     * private[executor] val _fetchWaitTime = new LongAccumulator
     * private[executor] val _recordsRead = new LongAccumulator
     */

    val shuffleMap = scala.collection.mutable.HashMap(
      "remoteBlocksFetched" -> shuffleReadMetrics.remoteBlocksFetched, //shuffle远程拉取数据块
      "localBlocksFetched" -> shuffleReadMetrics.localBlocksFetched, //本地块拉取
      "remoteBytesRead" -> shuffleReadMetrics.remoteBytesRead, //shuffle远程读取的字节数
      "localBytesRead" -> shuffleReadMetrics.localBytesRead, //读取本地数据的字节
      "fetchWaitTime" -> shuffleReadMetrics.fetchWaitTime, //拉取数据的等待时间
      "recordsRead" -> shuffleReadMetrics.recordsRead, //shuffle读取的记录总数
      "bytesWritten" -> shuffleWriteMetrics.bytesWritten, //shuffle写的总大小
      "recordsWritte" -> shuffleWriteMetrics.recordsWritten, //shuffle写的总记录数
      "writeTime" -> shuffleWriteMetrics.writeTime
    )

    val shuffleKey = s"shuffleKey${currentTimestamp}"
    jedis.set(shuffleKey, Json(DefaultFormats).write(shuffleMap))
    jedis.expire(shuffleKey, 3600)

    //=================输入输出========================
    val inputMetrics = taskEnd.taskMetrics.inputMetrics
    val outputMetrics = taskEnd.taskMetrics.outputMetrics

    val input_output = scala.collection.mutable.HashMap(
      "bytesRead" -> inputMetrics.bytesRead, //读取的大小
      "recordsRead" -> inputMetrics.recordsRead, //总记录数
      "bytesWritten" -> outputMetrics.bytesWritten,//输出的大小
      "recordsWritten" -> outputMetrics.recordsWritten//输出的记录数
    )
    val input_outputKey = s"input_outputKey${currentTimestamp}"
    jedis.set(input_outputKey, Json(DefaultFormats).write(input_output))
    jedis.expire(input_outputKey, 3600)



    //####################taskInfo#######
    val taskInfo: TaskInfo = taskEnd.taskInfo

    val taskInfoMap = scala.collection.mutable.HashMap(
      "taskId" -> taskInfo.taskId ,
      "host" -> taskInfo.host ,
      "speculative" -> taskInfo.speculative , //推测执行
      "failed" -> taskInfo.failed ,
      "killed" -> taskInfo.killed ,
      "running" -> taskInfo.running

    )

    val taskInfoKey = s"taskInfo${currentTimestamp}"
    jedis.set(taskInfoKey , Json(DefaultFormats).write(taskInfoMap))
    jedis.expire(taskInfoKey , 3600)

  }

trait StreamingListener {

  /** Called when a receiver has been started */
  def onReceiverStarted(receiverStarted: StreamingListenerReceiverStarted) { }

  /** Called when a receiver has reported an error */
  def onReceiverError(receiverError: StreamingListenerReceiverError) { }

  /** Called when a receiver has been stopped */
  def onReceiverStopped(receiverStopped: StreamingListenerReceiverStopped) { }

  /** Called when a batch of jobs has been submitted for processing. */
  def onBatchSubmitted(batchSubmitted: StreamingListenerBatchSubmitted) { }

  /** Called when processing of a batch of jobs has started.  */
  def onBatchStarted(batchStarted: StreamingListenerBatchStarted) { }

  /** Called when processing of a batch of jobs has completed. */
  def onBatchCompleted(batchCompleted: StreamingListenerBatchCompleted) { }

  /** Called when processing of a job of a batch has started. */
  def onOutputOperationStarted(
      outputOperationStarted: StreamingListenerOutputOperationStarted) { }

  /** Called when processing of a job of a batch has completed. */
  def onOutputOperationCompleted(
      outputOperationCompleted: StreamingListenerOutputOperationCompleted) { }
}

    val diskSpaceUsed_MB = gauges.getJSONObject(applicationId + ".driver.BlockManager.disk.diskSpaceUsed_MB").getLong("value")//使用的磁盘空间
    val maxMem_MB = gauges.getJSONObject(applicationId + ".driver.BlockManager.memory.maxMem_MB").getLong("value") //使用的最大内存
    val memUsed_MB = gauges.getJSONObject(applicationId + ".driver.BlockManager.memory.memUsed_MB").getLong("value")//内存使用情况
    val remainingMem_MB = gauges.getJSONObject(applicationId + ".driver.BlockManager.memory.remainingMem_MB").getLong("value") //闲置内存
    //#####################stage###################################
    val activeJobs = gauges.getJSONObject(applicationId + ".driver.DAGScheduler.job.activeJobs").getLong("value")//当前正在运行的job
    val allJobs = gauges.getJSONObject(applicationId + ".driver.DAGScheduler.job.allJobs").getLong("value")//总job数
    val failedStages = gauges.getJSONObject(applicationId + ".driver.DAGScheduler.stage.failedStages").getLong("value")//失败的stage数量
    val runningStages = gauges.getJSONObject(applicationId + ".driver.DAGScheduler.stage.runningStages").getLong("value")//正在运行的stage
    val waitingStages = gauges.getJSONObject(applicationId + ".driver.DAGScheduler.stage.waitingStages").getLong("value")//等待运行的stage
    //#####################StreamingMetrics###################################
    val lastCompletedBatch_processingDelay = gauges.getJSONObject(applicationId + ".driver.query.StreamingMetrics.streaming.lastCompletedBatch_processingDelay").getLong("value")// 最近批次执行的延迟时间
    val lastCompletedBatch_processingEndTime = gauges.getJSONObject(applicationId + ".driver.query.StreamingMetrics.streaming.lastCompletedBatch_processingEndTime").getLong("value")//最近批次执行结束时间（毫秒为单位）
    val lastCompletedBatch_processingStartTime = gauges.getJSONObject(applicationId + ".driver.query.StreamingMetrics.streaming.lastCompletedBatch_processingStartTime").getLong("value")//最近批次开始执行时间
    //执行时间
    val lastCompletedBatch_processingTime = (lastCompletedBatch_processingEndTime - lastCompletedBatch_processingStartTime)
    val lastReceivedBatch_records = gauges.getJSONObject(applicationId + ".driver.query.StreamingMetrics.streaming.lastReceivedBatch_records").getLong("value")//最近批次接收的数量
    val runningBatches = gauges.getJSONObject(applicationId + ".driver.query.StreamingMetrics.streaming.runningBatches").getLong("value")//正在运行的批次
    val totalCompletedBatches = gauges.getJSONObject(applicationId + ".driver.query.StreamingMetrics.streaming.totalCompletedBatches").getLong("value")//完成的数据量
    val totalProcessedRecords = gauges.getJSONObject(applicationId + ".driver.query.StreamingMetrics.streaming.totalProcessedRecords").getLong("value")//总处理条数
    val totalReceivedRecords = gauges.getJSONObject(applicationId + ".driver.query.StreamingMetrics.streaming.totalReceivedRecords").getLong("value")//总接收条数
    val unprocessedBatches = gauges.getJSONObject(applicationId + ".driver.query.StreamingMetrics.streaming.unprocessedBatches").getLong("value")//为处理的批次
    val waitingBatches = gauges.getJSONObject(applicationId + ".driver.query.StreamingMetrics.streaming.waitingBatches").getLong("value")//处于等待状态的批次

   val sparkDriverHost = sc.getConf.get("spark.org.apache.hadoop.yarn.server.webproxy.amfilter.AmIpFilter.param.PROXY_URI_BASES")
    //监控信息页面路径为集群路径+/proxy/+应用id+/metrics/json
  val url = s"${sparkDriverHost}/metrics/json"